no code implementations • 7 Apr 2022 • Violet Turri, Rachel Dzombak, Eric Heim, Nathan VanHoudnos, Jay Palat, Anusha Sinha
Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics.
no code implementations • 22 Jan 2021 • Jonathan M. Spring, April Galyardt, Allen D. Householder, Nathan VanHoudnos
This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if flaws in machine learning (ML) were assigned Common Vulnerabilities and Exposures (CVE) identifiers (CVE-IDs)?
1 code implementation • 18 Dec 2020 • Jonathan Helland, Nathan VanHoudnos
In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input gradients of their score functions and their subsequent adversarial perturbations.